1 Introdução

Este portfólio demonstra o que aprendi e sou capaz de fazer utilizando a linguagem R como ferramenta estatística e de modelagem de inteligência artificial.

2 Instalar e carregar bibliotecas

install.packages("dplyr")
library(dplyr)

install.packages("caret")
library(caret)

3 Criar vetores e matrizes e extrair subconjuntos deles

vetor <- c(1,2,3,4,5,6,7, 8, 9)
matriz <- matrix(vetor , nrow = 3)
vetor

[1] 1 2 3 4 5 6 7 8 9

vetor[1:3]

[1] 1 2 3

vetor[vetor < 6]

[1] 1 2 3 4 5

matriz

     [,1] [,2] [,3]
[1,]    1    4    7
[2,]    2    5    8
[3,]    3    6    9

matriz[1, 2]

[1] 4

matriz[, 3]

[1] 7 8 9

4 Manipular datas com a biblioteca Lubridate

library(lubridate)
data <- ymd("20190731")

um.ano.depois <- data + years(1)
um.ano.depois

[1] "2020-07-31"

5 Gerar números aleatórios seguindo distribuições de probabilidade

normal <- rnorm(100, mean = 5, sd = 2)
normal

  [1]  3.1277659  0.1684599  2.7418471 -0.2346442  6.2085593  5.5716705  4.0744676  6.8028021  7.2166787
 [10]  4.0338440  4.6780264  4.4888754  5.4182834  4.2039965  4.9063195  7.3497871  3.0388679  4.1575199
 [19]  3.3326817  4.5261037  8.0192970  4.2822641  2.1249156  5.3805223  5.1970747  5.5682728  5.8932552
 [28]  4.7527468  8.6907711  5.9201752  5.1779752  5.2843140  5.0133811  3.5442119  3.7282831  5.2485034
 [37]  4.8679826  5.3088418  6.6768776  1.8172700  5.8288302  8.0845784  5.4326765  5.2576235  4.3615531
 [46]  6.0309208  4.2384613  7.0101065  5.2480359  7.6080098  5.0803198  4.9606184  4.1293023  6.9487503
 [55]  2.5170328  3.5122507  4.7964694  4.0627517  4.3491371  3.0958915  2.2625576  8.0066741  5.6618914
 [64]  4.8169608  4.2531599  3.0105086  5.1646673  4.5956364  7.1907168  2.8023568  5.4818073  7.8501698
 [73]  3.9416546  8.1842647  3.7772834  3.7946262  5.5471808  5.0398361  4.9628027  5.5912824  3.2937300
 [82]  6.7017975  7.4043407  7.5052404  0.7527118  6.0102035  3.3182674  9.2304810  6.1407086  4.4644801
 [91]  3.0580821  8.4015841  6.2807730  3.0274393  4.9521353  4.4259306  4.4344114  4.2093162  2.0083353
[100]  7.5737060

binomial <- rbinom(100, 10, prob = 0.7)
binomial

  [1]  9  7  8  7  5  8  9  7  9  8  9  6  7  9  7  7  8  5  7  7  8  7  5  9  7  5  6  6  7  8  6  6  9  8  7
 [36]  5  8  5  9  5  6  5  9  5  7  7  8  9  4  8  9  5  8  8  6  8  9  5 10  8  8  6  7  4  9  7  8  6  6  7
 [71]  8  7  9  3  9  9  6  7  7  9  4  5  5  7  8  8  6  6  6  4  8  9  8 10  8  7  8 10  5  6

hist(normal)

hist(binomial)

boxplot(normal)

boxplot(binomial)

6 Manipular data frames

data(mtcars)

summary(mtcars)

      mpg             cyl             disp             hp             drat             wt       
 Min.   :10.40   Min.   :4.000   Min.   : 71.1   Min.   : 52.0   Min.   :2.760   Min.   :1.513  
 1st Qu.:15.43   1st Qu.:4.000   1st Qu.:120.8   1st Qu.: 96.5   1st Qu.:3.080   1st Qu.:2.581  
 Median :19.20   Median :6.000   Median :196.3   Median :123.0   Median :3.695   Median :3.325  
 Mean   :20.09   Mean   :6.188   Mean   :230.7   Mean   :146.7   Mean   :3.597   Mean   :3.217  
 3rd Qu.:22.80   3rd Qu.:8.000   3rd Qu.:326.0   3rd Qu.:180.0   3rd Qu.:3.920   3rd Qu.:3.610  
 Max.   :33.90   Max.   :8.000   Max.   :472.0   Max.   :335.0   Max.   :4.930   Max.   :5.424  
      qsec             vs               am              gear            carb      
 Min.   :14.50   Min.   :0.0000   Min.   :0.0000   Min.   :3.000   Min.   :1.000  
 1st Qu.:16.89   1st Qu.:0.0000   1st Qu.:0.0000   1st Qu.:3.000   1st Qu.:2.000  
 Median :17.71   Median :0.0000   Median :0.0000   Median :4.000   Median :2.000  
 Mean   :17.85   Mean   :0.4375   Mean   :0.4062   Mean   :3.688   Mean   :2.812  
 3rd Qu.:18.90   3rd Qu.:1.0000   3rd Qu.:1.0000   3rd Qu.:4.000   3rd Qu.:4.000  
 Max.   :22.90   Max.   :1.0000   Max.   :1.0000   Max.   :5.000   Max.   :8.000  

head(mtcars)

ids <- seq_len(nrow(mtcars))
set.seed(132)
amostra <- sample(ids, 6)
mtcars[amostra, ]

7 Criar funções

library(plotly)

plotWithTrendLine <- function (data, x, y) {
  fit <- data %>% lm(.[,y]~.[,x], data=.) 
  p <- plot_ly(data = data, x = data[, x], y = data[, y], type="scatter", mode='markers', 
               colors = c('#FF9999', 'lightblue'), opacity = 0.8) %>%
    add_trace(x=data[, x], y=predict(fit), mode = 'lines', line = list(color = 'lightblue'),
              showlegend = F, hoverinfo="none", inherit = FALSE) %>%
    layout(title = paste(y, 'vs', x, sep = ' '),
           xaxis = list(title = x, showline = T),
           yaxis = list(side = 'left', title = y))
  print(p)
}

plotWithTrendLine(mtcars, 'mpg', 'disp')

NULL

8 Baixar conteúdo da internet

file.url = 'https://poenaroda.com.br/wp-content/uploads/2019/02/destaque_alanturing.jpg'
file.local = file.path('./', basename(file.url))
download.file(url = file.url, destfile = file.local , mode='wb')

trying URL 'https://poenaroda.com.br/wp-content/uploads/2019/02/destaque_alanturing.jpg'
Content type 'image/jpeg' length 51027 bytes (49 KB)
==================================================
downloaded 49 KB

9 Ler arquivos CSV

setwd('~/workspace/fiap/wine')

The working directory was changed to /Users/felipe/workspace/fiap/wine inside a notebook chunk. The working directory will be reset when the chunk is finished running. Use the knitr root.dir option in the setup chunk to change the working directory for notebook chunks.

wines <- read.csv2(file="BaseWine_Red_e_White.csv"
                   , header=TRUE
                   , sep=";")

10 Padronizar dados

wines_padr <- preProcess(wines_adjusted[,1:11], c("center", "scale")) %>% 
  predict(., wines_adjusted) %>% 
  data.frame(trans = .)

colnames(wines_padr) <- colnames(wines_adjusted)

str(wines_padr)

'data.frame':   6497 obs. of  13 variables:
 $ fixedacidity      : num  -0.475 -0.397 2.611 -1.4 -0.397 ...
 $ volatileacidity   : num  -0.60537 0.00203 -0.18019 -0.96981 -0.24093 ...
 $ citricacid        : num  0.216 0.766 1.179 -0.541 0.835 ...
 $ residualsugar     : num  0.478 -0.813 -0.686 -0.135 2.817 ...
 $ chlorides         : num  -0.7146 -0.4291 0.1988 -0.4291 0.0276 ...
 $ freesulfurdioxide : num  0.3084 -0.0859 -0.7057 -0.0296 1.9423 ...
 $ totalsulfurdioxide: num  0.3407 -0.0309 -1.3401 -0.0486 1.9153 ...
 $ density           : num  -0.3019 -1.5394 0.983 -0.0821 1.6457 ...
 $ pH                : num  -0.1773 0.0715 -0.4882 1.2532 -0.6748 ...
 $ sulphates         : num  -1.08375 -0.61334 -0.14293 -0.88214 -0.00852 ...
 $ alcohol           : num  0.0114 1.739 -0.5645 -0.8936 -1.1404 ...
 $ quality           : int  5 6 6 6 5 5 4 6 7 6 ...
 $ type              : Factor w/ 2 levels "RED","WHITE": 2 2 1 2 2 1 1 1 2 2 ...

summary(wines_padr)

  fixedacidity     volatileacidity     citricacid       residualsugar       chlorides      
 Min.   :-2.6344   Min.   :-1.5772   Min.   :-2.19266   Min.   :-1.0243   Min.   :-1.3425  
 1st Qu.:-0.6289   1st Qu.:-0.6661   1st Qu.:-0.47230   1st Qu.:-0.7704   1st Qu.:-0.5148  
 Median :-0.1661   Median :-0.3017   Median :-0.05941   Median :-0.5164   Median :-0.2579  
 Mean   : 0.0000   Mean   : 0.0000   Mean   : 0.00000   Mean   : 0.0000   Mean   : 0.0000  
 3rd Qu.: 0.3739   3rd Qu.: 0.3665   3rd Qu.: 0.49111   3rd Qu.: 0.5629   3rd Qu.: 0.2559  
 Max.   : 6.6989   Max.   : 7.5338   Max.   : 9.23057   Max.   : 8.5416   Max.   :15.8410  
 freesulfurdioxide  totalsulfurdioxide    density               pH             sulphates      
 Min.   :-1.66345   Min.   :-1.9416    Min.   :-2.56383   Min.   :-3.10038   Min.   :-2.0918  
 1st Qu.:-0.76202   1st Qu.:-0.6855    1st Qu.:-0.79551   1st Qu.:-0.67481   1st Qu.:-0.6805  
 Median :-0.08594   Median : 0.0399    Median : 0.06668   Median :-0.05287   Median :-0.1429  
 Mean   : 0.00000   Mean   : 0.0000    Mean   : 0.00000   Mean   : 0.00000   Mean   : 0.0000  
 3rd Qu.: 0.59014   3rd Qu.: 0.7122    3rd Qu.: 0.77672   3rd Qu.: 0.63126   3rd Qu.: 0.4619  
 Max.   :14.56245   Max.   : 5.7368    Max.   : 6.52124   Max.   : 4.92265   Max.   : 9.8701  
    alcohol           quality         type     
 Min.   :-7.8396   Min.   :3.000   RED  :1599  
 1st Qu.:-0.8113   1st Qu.:5.000   WHITE:4898  
 Median :-0.1532   Median :6.000               
 Mean   : 0.0000   Mean   :5.818               
 3rd Qu.: 0.6695   3rd Qu.:6.000               
 Max.   : 3.6311   Max.   :9.000               

11 Usar o dplyr

wines_adjusted <- wines %>% select(-id_vinho) %>% rename(type = Vinho)
head(wines_adjusted)

12 Criar gráficos

wines_adjusted %>%
  ggplot(aes(x = density, y = fixedacidity, color = type)) +
   geom_point(alpha = 0.2, size = 2) +
   geom_smooth(method = 'lm')

plot(airquality$Wind, airquality$Ozone)

13 Clusterização com K-Means

set.seed(1232)
output_cluster <- kmeans(wines_padr, 6, iter=100)
output_cluster

K-means clustering with 6 clusters of sizes 946, 1206, 1483, 1219, 646, 997

Cluster means:
  fixedacidity volatileacidity  citricacid residualsugar  chlorides freesulfurdioxide totalsulfurdioxide
1   0.08473360       1.6866294 -1.26213820    -0.6317944  0.6817667        -0.7986723        -1.16915557
2  -0.52520677      -0.2668938 -0.02511597    -0.4822657 -0.5802020        -0.1213941        -0.16797325
3  -0.17028943      -0.3492428  0.31064945     1.4659004 -0.1443988         0.9372052         0.99798842
4   0.09639664      -0.4497086  0.23995436    -0.2777307 -0.2107031        -0.2721956         0.07332153
5   2.00659014       0.5019104  0.95725823    -0.5616504  1.2624821        -0.8942313        -1.25067366
6  -0.60981357      -0.5333900 -0.14775699    -0.2941430 -0.2906727         0.4228183         0.54878266
     density          pH   sulphates     alcohol
1  0.5037673  0.96129972  0.40065402 -0.24807743
2 -1.3589390 -0.04482517 -0.30296210  1.39885650
3  0.9223711 -0.49867076 -0.27728431 -0.84938155
4 -0.4284112 -0.72419807 -0.50528600 -0.08757578
5  1.0021260 -0.06731150  1.42050025  0.02119780
6 -0.3316950  0.81291779  0.09615516 -0.09994560

Clustering vector:
   [1] 4 2 5 6 3 1 1 1 2 3 3 6 6 6 4 2 1 4 1 6 6 3 1 4 4 4 6 5 1 3 2 1 5 4 1 6 6 3 2 3 3 3 6 5 2 3 4 3 2 2 4
  [52] 2 6 6 1 6 4 6 1 1 2 3 4 4 1 2 4 5 2 3 6 4 3 1 4 5 5 6 2 3 2 2 5 5 5 1 2 3 1 2 5 6 2 2 3 2 3 4 2 2 1 4
 [103] 2 4 6 1 4 2 4 6 3 4 4 4 4 3 2 4 6 2 4 6 5 3 6 3 4 6 1 1 6 5 6 2 3 1 1 3 4 3 3 3 2 3 2 2 5 3 1 1 6 4 4
 [154] 2 1 6 3 3 5 3 3 6 3 5 2 2 1 4 6 4 1 1 3 3 2 6 2 1 6 3 2 1 4 1 4 6 3 6 1 3 4 1 3 2 5 2 6 3 2 3 4 2 3 6
 [205] 3 6 3 6 5 3 1 2 6 5 5 6 3 2 4 3 3 3 4 4 3 1 1 4 2 3 1 2 4 3 1 4 3 1 5 3 5 1 1 3 2 6 6 6 3 2 4 6 2 2 4
 [256] 3 5 3 3 3 3 1 1 2 1 2 2 6 4 3 2 4 3 3 1 5 2 3 5 1 2 3 5 1 6 5 2 5 3 2 3 6 2 2 1 6 1 3 5 6 3 3 1 5 4 3
 [307] 2 1 1 3 4 1 5 1 2 3 1 4 1 1 4 6 6 3 6 2 4 1 1 3 5 4 3 3 5 1 4 3 5 3 2 5 4 3 6 6 1 5 4 2 2 4 4 6 4 4 3
 [358] 2 6 6 4 2 3 2 6 1 2 3 2 4 3 4 3 1 4 1 2 6 4 6 5 5 3 6 3 1 2 4 2 2 1 2 6 5 3 6 5 1 4 4 1 4 3 4 2 3 6 2
 [409] 5 1 4 4 2 6 3 6 4 3 5 1 2 3 3 3 3 3 2 6 2 2 6 1 2 2 4 1 3 4 2 2 3 4 3 3 3 3 1 6 1 1 6 4 4 4 6 3 3 2 4
 [460] 4 2 3 1 6 6 4 2 6 4 2 2 2 2 4 3 4 6 3 6 2 4 5 2 2 6 6 3 2 4 3 4 4 2 4 2 1 3 4 5 3 2 4 6 2 4 6 5 6 4 6
 [511] 5 4 1 6 3 3 5 6 2 3 1 1 3 6 6 4 6 3 6 4 6 2 2 1 6 2 1 3 1 6 3 4 1 4 2 5 6 6 1 4 3 3 3 6 2 6 5 2 5 6 4
 [562] 2 3 3 6 2 3 6 2 5 4 4 6 2 4 4 3 3 3 2 6 5 2 4 3 3 5 2 1 3 4 1 1 3 1 2 3 3 2 3 4 3 3 3 5 1 1 1 1 4 3 4
 [613] 4 4 5 3 2 1 6 5 2 2 4 4 2 1 1 1 2 2 3 5 1 6 3 3 4 4 3 5 2 3 4 3 2 2 6 6 3 3 3 2 4 5 2 2 1 3 2 5 5 2 2
 [664] 5 5 3 6 4 2 1 6 3 4 2 4 2 3 1 4 3 1 4 5 3 3 2 1 4 3 4 1 1 2 2 1 2 3 3 3 3 2 5 4 2 1 2 4 3 2 1 6 1 2 4
 [715] 3 4 3 4 2 6 3 3 6 3 3 6 6 4 6 4 4 1 2 6 3 3 6 2 5 5 3 4 2 4 1 2 2 1 2 5 5 1 6 5 6 6 2 5 1 1 6 1 4 2 1
 [766] 2 5 3 6 1 3 1 3 6 2 5 2 4 4 2 3 4 4 2 1 6 2 6 6 1 1 5 6 4 5 4 3 1 4 2 2 4 6 4 1 6 3 1 1 4 4 3 3 5 3 6
 [817] 5 4 6 6 1 1 5 1 6 4 3 1 2 4 4 6 3 3 4 4 4 3 4 4 4 1 3 6 3 3 3 6 2 5 5 6 4 3 4 2 4 2 3 1 2 2 2 5 6 4 1
 [868] 6 6 3 4 3 4 6 5 4 6 2 6 5 1 1 2 1 2 4 5 6 3 4 2 1 2 2 5 6 6 1 2 4 1 2 3 2 3 3 3 1 3 4 1 2 4 3 6 5 3 1
 [919] 5 2 2 4 1 4 1 4 1 2 4 6 6 1 3 2 2 6 5 3 6 4 5 1 4 5 1 6 1 1 6 6 2 2 2 6 4 2 1 2 3 2 2 2 3 3 5 6 3 6 5
 [970] 5 3 5 2 1 1 2 6 4 2 2 2 4 5 3 3 6 6 2 6 1 6 1 4 3 2 6 5 6 3 4
 [ reached getOption("max.print") -- omitted 5497 entries ]

Within cluster sum of squares by cluster:
[1] 5121.289 4905.915 7942.310 5922.045 7546.492 4797.123
 (between_SS / total_SS =  49.3 %)

Available components:

[1] "cluster"      "centers"      "totss"        "withinss"     "tot.withinss" "betweenss"    "size"        
[8] "iter"         "ifault"      

table(output_cluster$cluster)

   1    2    3    4    5    6 
 946 1206 1483 1219  646  997